Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add justincampbell/gh-watch --skill watch-prgit clone --depth 1 https://github.com/justincampbell/gh-watchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/justincampbell/gh-watch/watch-pr)<a href="https://agentmods.dev/skills/justincampbell/gh-watch/watch-pr"><img src="https://agentmods.dev/badge/skills/justincampbell/gh-watch/watch-pr/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/justincampbell/gh-watch/watch-pr"><img src="https://agentmods.dev/badge/skills/justincampbell/gh-watch/watch-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00048 | $0.01136 |
| Opus 5 | $0.00024 | $0.00568 |
| Sonnet 5 | $0.00010 | $0.00227 |
| Haiku 4.5 | $0.00005 | $0.00114 |
Grade A, and why
watch-pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Watch a Pull Request
Monitor a pull request for state changes using the gh watch CLI extension. It polls GitHub and emits one JSON event per line to stdout, which makes it a natural fit for the Monitor tool — each event arrives in the conversation as a notification.
Prerequisites
Check if the extension is installed:
gh watch --help
If not installed:
gh extension install justincampbell/gh-watch
Usage
Run with the Monitor tool (not Bash with run_in_background). Each stdout line — starting with initial-state — is delivered as a notification, so you react to events as they land instead of polling an output file.
Wait for CI to finish, then exit — use a bounded timeout_ms and let --exit-on end the watch:
command:gh watch pr $ARGUMENTS --exit-on ci-passed,ci-failed,pr-merged,pr-closeddescription:PR $ARGUMENTS CI statuspersistent:falsetimeout_ms:1800000(30 min — raise for slow CI)
Wait for a code review:
command:gh watch pr $ARGUMENTS --exit-on review-submitted
Wait until a queued PR resolves (merges or gets kicked out of the merge queue):
command:gh watch pr $ARGUMENTS --exit-on pr-merged,merge-queue-removed
Watch the PR for the rest of the session (CI + reviews + comments + merge state):
command:gh watch pr $ARGUMENTSdescription:PR $ARGUMENTS state changespersistent:true(no timeout — stop withTaskStopor end of session)
If no PR number is provided, the PR for the current branch is detected automatically. To watch a PR in another repo, prefix the command with GH_REPO=owner/repo (the pr subcommand takes a number, not a URL).
Flags
| Flag | Description | Default |
|---|---|---|
--interval <duration> |
Polling interval | 60s |
--exit |
Exit after any state change | false |
--exit-on <events> |
Exit after specific event types (comma-separated) |
Event types
| Event | Description |
|---|---|
initial-state |
Snapshot of PR state at the moment watching started (always emitted first) |
ci-passed |
All CI checks passed |
ci-failed |
CI failed (at least one check failed) |
review-submitted |
A review was submitted |
comment-added |
A new comment was posted |
merge-conflict-changed |
Mergeable state changed |
merge-queue-entered |
PR was added to the merge queue |
merge-queue-status-changed |
Merge queue entry changed state (e.g. AWAITING_CHECKS → UNMERGEABLE) |
merge-queue-removed |
PR left the merge queue without merging (e.g. kicked out on failure) |
pr-merged |
PR was merged (terminal — always exits) |
pr-closed |
PR was closed (terminal — always exits) |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 101 lines · 48 tokens per session scan A 8e2a16c6784f
watch-pr is a skill published in the GitHub repository justincampbell/gh-watch (4 stars, last pushed 22d ago), licensed MIT. It adds 48 tokens to every session and 1,136 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
bellwether
Bring the current PR to a mergeable state: CI green, all review comments resolved, no merge conflicts. Self-contained — watches CI, fixes issues, watches again until merge-ready. Use when the user wants to keep a PR green, auto-fix CI, resolve review comments, or says "get this merged".
argot-setup
Set argot up for a repository end to end — audit its history, decide what should shape its voice, fit, verify the fit actually catches things, tune the rules its own history says are noisy, and wire the places it runs (pre-write hook, pre-commit, MCP, CI). One sitting, one decision at a time, each proposed with the…
detect-task
Internal skill for commands. Detect the active task (any tracker adapter) from the task-state file / git branch name. Do not trigger on user conversation - only when commands need task detection.
loop-bb-pr
A command that prepares a repeating check for a Bitbucket pull request. A pull request is a request to review and merge code changes into a project.
take-task
A workflow for claiming a tracker task and preparing the development branch for it. It verifies the task, marks it as in progress, checks for uncommitted changes, and handles branch setup according to the task state.
session-boundary
Internal skill for commands. Resolve and VALIDATE this branch's session boundary - the ref a session's commit range is measured from - and report how much it can be trusted. Do not trigger on user conversation; only when a command needs the session range.